vak.transforms.transforms#
Classes
|
Add a "channel" dimension to a tensor. |
|
pad a 1d or 2d array so that it can be reshaped into consecutive windows of specified size |
|
transform that standardizes spectrograms so they are all on the same scale, by subtracting off the mean and dividing by the standard deviation from a 'fit' set of spectrograms. |
convert Numpy array to torch.FloatTensor. |
|
convert Numpy array to torch.LongTensor. |
|
|
return view of a 1d or 2d array as a batch of non-overlapping windows |